Recognition model with narrow and broad extension fields

A recognition model which de®nes a measure of shape similarity on the direct output of multiscale and multiorientation Gabor ®lters does not manifest qualitative aspects of human object recognition of contour-deleted images in that: (a) it recognizes recoverable and nonrecoverable contour-deleted images equally well whereas humans recognize recoverable images much better, (b) it distinguishes complementary feature-deleted images whereas humans do not. Adding some of the known connectivity pattern of the primary visual cortex to the model in the form of extension ®elds (connections between collinear and curvilinear units) among ®lters increased the overall recognition performance of the model and: (a) boosted the recognition rate of the recoverable images far more than the nonrecoverable ones, and (b) increased the similarity of complementary feature-deleted images, but not part-deleted ones, and thus attained a closer correspondence to human psychophysical results. Interestingly, performance was approximately equivalent for narrow … 15°† and broad … 90°† extension ®elds. Ó 2000 Published by Elsevier Science Inc. All rights reserved.